AI agents use move_task to create or update resources in Omniplan — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Omniplan environment.
Moving a task modifies project structure and task properties reversibly—it reorders or reorganizes tasks without deletion. This is a Write operation (data modification) rather than Read (no side effects) or Destructive (irreversible). Severity is medium because misuse could corrupt project schedules or task dependencies, affecting workflow, but changes can be undone. Confidence is slightly reduced (0.85 vs.
From the tool's definition Tool named 'move_task' on an OmniPlan project management server that 'allows creation and manipulation of tasks' and 'project metadata'.
Attacks that exploit this kind of access
move_task. It is categorised as a Write tool in the Omniplan MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Omniplan MCP server in PolicyLayer and add a rule for move_task: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Omniplan. Nothing to install.
move_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the move_task rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for move_task. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
move_task is provided by the Omniplan MCP server (johntrandall/omniplan-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →